The possible impact of weather on crimes in Amsterdam

import pandas as pd
from pandas import Timedelta
import numpy as np
import plotly.express as px
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from IPython.display import display, Markdown
import plotly.io as pio
pio.renderers.default = "notebook"
import plotly.graph_objects as go
df = pd.read_csv("merged_weather_misdrijven_monthly_v3.csv")

Perspective 1: Pleasant weather increases the risk of certain crimes

Argument 1.1 Higher temperatures lead to more bicycle theft

In Amsterdam, cycling is the main form of transport. Better weather conditions encourage more outside activity such as events or going to the beach, which means more transport and bikes being left outside. This should be the optimal climate for bicycle theft and supports the idea that weather has an influence on crime. To look into this relationship between theft and tropical weather, we inspect temperature and the rates of bicycle theft in the graph below.

df.columns = df.columns.str.strip()
df['TX'] = df['TX'] / 10  # TX is in tienden van °C
df['TG'] = df['TG'] / 10  # TG is in tienden van °C
display(Markdown("### Bicycle Theft vs. Maximum Temperature"))
display(Markdown("_Slight increase in thefts when it's warmer._"))

# 📈 Plot maken
plt.figure(figsize=(8, 5))
sns.regplot(
    x='TX',
    y='1.2.3 Diefstal van brom-, snor-, fietsen',
    data=df,
    scatter_kws={'alpha': 0.5}
)
plt.xlabel("Maximum Temperature (°C)")
plt.ylabel("Number of Bicycle Thefts")
plt.grid(True)
plt.tight_layout()
plt.show()

Bicycle Theft vs. Maximum Temperature

Slight increase in thefts when it’s warmer.

This scatterplot shows the relationship between monthly maximum temperature (°C) on the horizontal axis and the number of bicycle thefts reported in the Netherlands on the vertical axis. Each point represents one month. The blue regression line indicates a slight upward trend: bicycle thefts do appear to increase when temperatures are higher. Pearson’s correlation between the two is 0.502, which is considered moderate. To put it more intuitively: every single degree that a day gets warmer, an average of 13.23 more bicycles are stolen. This result supports the first argument, since warmer weather seems to mean more bike theft.

Argument 1.2 Alcohol-related incidents on the water increase with sunshine

# Titel en korte take-away boven de plot
display(Markdown("### Weather vs. Water-Related Influence Reports"))
display(Markdown("_Higher temperature and evaporation coincide with more 'under influence on boat' incidents._"))

df['year_month'] = pd.to_datetime(df['year_month'])
df['SQ'] = df['SQ'] / 10  # TG is in tienden van °C
fig, ax = plt.subplots(figsize=(12,6))

ax.plot(df['year_month'], df['SQ'], label='Sunshine duration (hours)', color='blue')
ax.plot(df['year_month'], df['3.4.2 Onder invloed (water)'], label='Under influence on boat', color='green')

# X-as labels
ax.set_xlabel('Month, grouped by year')
ax.set_ylabel('Value')
ax.set_title('Temperature, Evaporation and Water-Influence Reports Over Time')

# Zet alle maandticks maar zonder labels
ax.xaxis.set_major_locator(mdates.MonthLocator())
ax.xaxis.set_major_formatter(mdates.DateFormatter(''))

# Maak blokken per jaar (lichte achtergrond)
years = df['year_month'].dt.year.unique()
for year in years:
    start = pd.Timestamp(f'{year}-01-01')
    end = pd.Timestamp(f'{year}-12-31')
    ax.axvspan(start, end, color='lightgrey', alpha=0.2)

# Haak-achtige lijnen en jaartallabels onder de x-as
ylim = ax.get_ylim()
y_base = ylim[0] - 0.05*(ylim[1]-ylim[0])          # basislijn net onder x-as
y_hook_top = y_base + 0.02*(ylim[1]-ylim[0])       # top van haakjes

for year in years:
    start = pd.Timestamp(f'{year}-01-01')
    end = pd.Timestamp(f'{year}-12-31')

    # horizontale lijn (onder het jaarblok)
    ax.hlines(y=y_base, xmin=start, xmax=end, colors='black', linewidth=1.5)

    # verticale lijntjes aan begin en eind als haakjes
    ax.vlines(x=start, ymin=y_base, ymax=y_hook_top, colors='black', linewidth=1.5)
    ax.vlines(x=end, ymin=y_base, ymax=y_hook_top, colors='black', linewidth=1.5)

    # jaarlabel gecentreerd tussen de haakjes, iets onder de lijn
    mid = pd.Timestamp(f'{year}-07-01')
    ax.text(mid, y_base - 0.02*(ylim[1]-ylim[0]), str(year), ha='center', va='top', fontsize=12)

# Optioneel nog grid, legend en layout
ax.grid(True)
ax.legend()
fig.tight_layout()
start_lim = df['year_month'].min() - Timedelta(days=20)
end_lim = df['year_month'].max() + Timedelta(days=300)
ax.set_xlim(start_lim, end_lim)
plt.show()

Weather vs. Water-Related Influence Reports

Higher temperature and evaporation coincide with more ‘under influence on boat’ incidents.

plt.figure(figsize=(10,6))

sns.regplot(data=df, x='VVN', y='1.1.1 Diefstal/inbraak woning', scatter_kws={'s':50}, line_kws={'color':'red'})

plt.title('Lower Visibility May Be Linked to More Home Burglaries')

plt.xlabel('Average Monthly Minimum Visibility (VVN scale, higher = better visibility)')
plt.ylabel('Total Burglary Incidents per Month')

plt.grid(True)


plt.show()

weer_vars = ['TG', 'RH', 'VVN']
misdaad_vars = [
    '1.1.1 Diefstal/inbraak woning',
    '1.3.1 Ongevallen (weg)',
    '3.4.2 Onder invloed (water)',
    '1.4.2 Moord, doodslag',
    '2.5.2 Winkeldiefstal',
    '1.2.4 Zakkenrollerij',
    '1.2.3 Diefstal van brom-, snor-, fietsen'
]

# Maak subset dataframe met weer en misdaad kolommen
df_subset = df[weer_vars + misdaad_vars]

# Bereken correlatie matrix
corr_matrix = df_subset.corr()

# Selecteer alleen correlaties tussen weer_vars (rijen) en misdaad_vars (kolommen)
corr_submatrix = corr_matrix.loc[weer_vars, misdaad_vars]

crime_translation = {
    '1.1.1 Diefstal/inbraak woning': 'Burglary (home)',
    '1.3.1 Ongevallen (weg)': 'Traffic Accidents',
    '3.4.2 Onder invloed (water)': 'Under Influence (water)',
    '1.4.2 Moord, doodslag': 'Murder / Manslaughter',
    '2.5.2 Winkeldiefstal': 'Shoplifting',
    '1.2.4 Zakkenrollerij': 'Pickpocketing',
    '1.2.3 Diefstal van brom-, snor-, fietsen': 'Bicycle Theft'
}

corr_submatrix.columns = corr_submatrix.columns.map(crime_translation)

# Optioneel: weer variabelen vertalen (indien gewenst)
weather_translation = {
    'TG': 'Avg. Temperature',
    'RH': 'Precipitation (mm)',
    'VVN': 'Min Visibility (hm)'
}
corr_submatrix.index = corr_submatrix.index.map(weather_translation)

import matplotlib.pyplot as plt
import seaborn as sns

plt.figure(figsize=(12, 6))
sns.heatmap(
    corr_submatrix,
    annot=True,
    cmap='coolwarm',
    center=0,
    vmin=-0.6,
    vmax=0.6
)

plt.title('Correlation between Weather Variables and Crime Categories')
plt.xlabel('Crime Categories')
plt.ylabel('Weather Variables')
plt.xticks(rotation=45, ha='right')
plt.tight_layout()
plt.show()

# Map each month number to a season
season_map = {
    1: 'Winter', 2: 'Winter', 12: 'Winter',
    3: 'Spring', 4: 'Spring', 5: 'Spring',
    6: 'Summer', 7: 'Summer', 8: 'Summer',
    9: 'Autumn', 10: 'Autumn', 11: 'Autumn'
}

# Extract numeric month from 'year_month' and map to season
df['month'] = pd.to_datetime(df['year_month']).dt.month
df['Season'] = df['month'].map(season_map)

# Serious crime columns and their display names
serious_crimes = {
    '1.4.2 Moord, doodslag': 'Murder',
    '1.4.5 Mishandeling': 'Abuse',
    '3.7.4 Cybercrime': 'Cybercrime'
}

# Create pie charts
fig, axes = plt.subplots(1, 3, figsize=(18, 6))

for ax, (col, label) in zip(axes, serious_crimes.items()):
    # Total incidents per season for each crime
    season_totals = df.groupby('Season')[col].sum().reindex(['Winter', 'Spring', 'Summer', 'Autumn'])

    # Pie chart
    ax.pie(
        season_totals,
        labels=season_totals.index,
        autopct='%1.1f%%',
        startangle=90,
        colors=sns.color_palette("pastel")[0:4]
    )
    ax.set_title(f'Seasonal Distribution of {label}')

# Title and caption
fig.suptitle('Serious Crimes Occur Steadily Across All Seasons', fontsize=16)
plt.tight_layout()
plt.show()

crime_columns = {
    'Burglary (home)': '1.1.1 Diefstal/inbraak woning',
    'Traffic Accidents':'1.3.1 Ongevallen (weg)',
    'Under Influence (water)': '3.4.2 Onder invloed (water)',
    'Murder / Manslaughter': '1.4.2 Moord, doodslag',
    'Shoplifting': '2.5.2 Winkeldiefstal',
    'Pickpocketing': '1.2.4 Zakkenrollerij',
    'Bicycle Theft': '1.2.3 Diefstal van brom-, snor-, fietsen'    
}

def create_slider_plot(df):
    temps = [round(t, 1) for t in list(frange(5.0, 26.5, 0.5))]
    fig = go.Figure()

    # Voeg alle frames toe, één per temperatuur
    frames = []
    for temp in temps:
        lower, upper = temp - 0.5, temp + 0.5
        filtered = df[(df['TX'] >= lower) & (df['TX'] < upper)]
        y = [ (filtered[col].sum() / df[col].sum()) * 100 if df[col].sum() > 0 else 0
              for col in crime_columns.values() ]
        frames.append(go.Frame(
            data=[go.Bar(x=list(crime_columns.keys()), y=y)],
            name=f"{temp}"
        ))

    # Voeg eerste data toe als initiele trace
    fig.add_trace(frames[0].data[0])

    # Zet layout, slider en frames
    fig.update_layout(
        title="Crime Distribution by Temperature",
        yaxis=dict(range=[0,25], title="Pct of Total Incidents"),
        xaxis_title="Crime Type",
        width=800, height=600,
        updatemenus=[dict(
            type="buttons",
            showactive=False,
            buttons=[dict(label="Play", method="animate",
                          args=[None, {"frame": {"duration": 300, "redraw": True},
                                       "fromcurrent": True, "transition": {"duration": 0}}])]
        )],
        sliders=[dict(
            active=temps.index(20.0),
            currentvalue={"prefix": "Temp: "},
            pad={"t": 50},
            steps=[dict(label=f"{t}°C", method="animate", args=[[str(t)], {"frame": {"duration": 0}, "mode": "immediate"}])
                   for t in temps]
        )]
    )
    fig.frames = frames
    return fig

def frange(start, stop, step):
    while start <= stop:
        yield round(start, 1)
        start += step

fig = create_slider_plot(df)
fig.show()